FormalASR: End-to-End Spoken Chinese to Formal Text
For developers of writing-oriented applications, this work provides a lightweight, on-device solution to convert spoken Chinese into formal text, eliminating the latency and memory costs of two-stage ASR+LLM pipelines.
FormalASR introduces two compact end-to-end models (0.6B and 1.7B) that directly transcribe spoken Chinese into formal written text, achieving up to 37.4% relative CER reduction over verbatim baselines without requiring a post-processing LLM.
Automatic speech recognition (ASR) systems are typically optimized for verbatim transcription, which preserves disfluencies, filler words, and informal spoken structures that are often unsuitable for downstream writing-oriented applications. A common workaround is a two-stage ASR+LLM pipeline for post-editing, but this design increases latency and memory cost and is difficult to deploy on-device. We present FormalASR, two compact end-to-end models (0.6B and 1.7B) that directly transcribe spoken Chinese into formal written text. To enable this setting, we build WenetSpeech-Formal and Speechio-Formal, two large-scale spoken-to-formal datasets constructed by LLM-based rewriting and quality filtering. We then fine-tune Qwen3-ASR at two scales (0.6B and 1.7B) with supervised fine-tuning. Experiments on WenetSpeech-Formal and Speechio-Formal show that FormalASR achieves up to 37.4% relative CER reduction over verbatim baselines, while also improving ROUGE-L and BERTScore. FormalASR requires no post-processing LLM at deployment time, providing a lightweight, on-device solution for spoken-to-formal transcription.